Imperial College London > Talks@ee.imperial > Complexity & Networks Group > Learning strict Nash Equilibria through reinformcement
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Learning strict Nash Equilibria through reinformcementAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Henrik J Jensen. This paper studies the analytical properties of the reinforcement learning model proposed in Erev and Roth (1998), also termed cumulative reinforcement learning in Laslier et al. (2001). This stochastic model of learning in games accounts for two main elements: the law of effect (positive reinforcement of actions that perform well) and the law of practice (the magnitude of the reinforcement effect decreases with players’ experience). The main results of the paper show that, if the solution trajectories of the underlying replicator equation converge exponentially fast, then, with probability arbitrarily close to one, all the realizations of the reinforcement learning process lie within an ǫ band of that solution. The paper improves upon results currently available in the literature by showing that a reinforcement learning process that has been running for some time and is found sufficiently close to a strict Nash equilibrium, will reach it with probability one. This talk is part of the Complexity & Networks Group series. This talk is included in these lists:Note that ex-directory lists are not shown. |
Other listsThe FuturICT Flagship: Creating Socially Interactive Information Technologies for a Sustainable Future COMMSP Seminar Type the title of a new list hereOther talksA model of visual time perception Analysis and design of extremum seeking controllers Controlled quantum dynamics |